Fully Hyperbolic Neural Networks
- URL: http://arxiv.org/abs/2105.14686v1
- Date: Mon, 31 May 2021 03:36:49 GMT
- Title: Fully Hyperbolic Neural Networks
- Authors: Weize Chen, Xu Han, Yankai Lin, Hexu Zhao, Zhiyuan Liu, Peng Li,
Maosong Sun, Jie Zhou
- Abstract summary: We propose a fully hyperbolic framework to build hyperbolic networks based on the Lorentz model.
We show that our method has better performance for building both shallow and deep networks.
- Score: 63.22521652077353
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Hyperbolic neural networks have shown great potential for modeling complex
data. However, existing hyperbolic networks are not completely hyperbolic, as
they encode features in a hyperbolic space yet formalize most of their
operations in the tangent space (a Euclidean subspace) at the origin of the
hyperbolic space. This hybrid method greatly limits the modeling ability of
networks. In this paper, we propose a fully hyperbolic framework to build
hyperbolic networks based on the Lorentz model by adapting the Lorentz
transformations (including boost and rotation) to formalize essential
operations of neural networks. Moreover, we also prove that linear
transformation in tangent spaces used by existing hyperbolic networks is a
relaxation of the Lorentz rotation and does not include the boost, implicitly
limiting the capabilities of existing hyperbolic networks. The experimental
results on four NLP tasks show that our method has better performance for
building both shallow and deep networks. Our code will be released to
facilitate follow-up research.
Related papers
- Hypformer: Exploring Efficient Hyperbolic Transformer Fully in Hyperbolic Space [47.4014545166959]
We introduce Hypformer, a novel hyperbolic Transformer based on the Lorentz model of hyperbolic geometry.
We develop a linear self-attention mechanism in hyperbolic space, enabling hyperbolic Transformer to process billion-scale graph data and long-sequence inputs for the first time.
arXiv Detail & Related papers (2024-07-01T13:44:38Z) - Hyperbolic vs Euclidean Embeddings in Few-Shot Learning: Two Sides of
the Same Coin [49.12496652756007]
We show that the best few-shot results are attained for hyperbolic embeddings at a common hyperbolic radius.
In contrast to prior benchmark results, we demonstrate that better performance can be achieved by a fixed-radius encoder equipped with the Euclidean metric.
arXiv Detail & Related papers (2023-09-18T14:51:46Z) - Fully Hyperbolic Convolutional Neural Networks for Computer Vision [3.3964154468907486]
We present HCNN, a fully hyperbolic convolutional neural network (CNN) designed for computer vision tasks.
Based on the Lorentz model, we propose novel formulations of the convolutional layer, batch normalization, and multinomial logistic regression.
Experiments on standard vision tasks demonstrate the promising performance of our HCNN framework in both hybrid and fully hyperbolic settings.
arXiv Detail & Related papers (2023-03-28T12:20:52Z) - A Unification Framework for Euclidean and Hyperbolic Graph Neural
Networks [8.080621697426997]
Hyperbolic neural networks can effectively capture the inherent hierarchy of graph datasets.
They entangle multiple incongruent (gyro-)vector spaces within a layer, which makes them limited in terms of generalization and scalability.
We propose the Poincare disk model as our search space, and apply all approximations on the disk.
We demonstrate that our model not only leverages the power of Euclidean networks such as interpretability and efficient execution of various model components, but also outperforms both Euclidean and hyperbolic counterparts on various benchmarks.
arXiv Detail & Related papers (2022-06-09T05:33:02Z) - Trivial bundle embeddings for learning graph representations [9.070194145842489]
We propose an inductive model that learns inductive node representations for networks with or without node features.
In practice, it reduces errors for link prediction and node classification when compared to the Euclidean and hyperbolic GCNs.
arXiv Detail & Related papers (2021-12-05T10:26:46Z) - Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN
Design [8.250374560598493]
Hyperbolic neural networks have been popular in the recent past due to their ability to represent hierarchical data sets effectively and efficiently.
The challenge in developing these networks lies in the nonlinearity of the embedding space namely, the Hyperbolic space.
We present a novel fully hyperbolic neural network which uses the concept of projections (embeddings) followed by an intrinsic aggregation and a nonlinearity all within the hyperbolic space.
arXiv Detail & Related papers (2021-12-03T03:20:27Z) - Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs [77.33781731432163]
We learn dynamic graph representation in hyperbolic space, for the first time, which aims to infer node representations.
We present a novel Hyperbolic Variational Graph Network, referred to as HVGNN.
In particular, to model the dynamics, we introduce a Temporal GNN (TGNN) based on a theoretically grounded time encoding approach.
arXiv Detail & Related papers (2021-04-06T01:44:15Z) - Hyperbolic Neural Networks++ [66.16106727715061]
We generalize the fundamental components of neural networks in a single hyperbolic geometry model, namely, the Poincar'e ball model.
Experiments show the superior parameter efficiency of our methods compared to conventional hyperbolic components, and stability and outperformance over their Euclidean counterparts.
arXiv Detail & Related papers (2020-06-15T08:23:20Z) - Differentiating through the Fr\'echet Mean [51.32291896926807]
Fr'echet mean is a generalization of the Euclidean mean.
We show how to differentiate through the Fr'echet mean for arbitrary Riemannian manifold.
This fully integrates the Fr'echet mean into the hyperbolic neural network pipeline.
arXiv Detail & Related papers (2020-02-29T19:49:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.